Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add RobotRegistryFoundation/robot-md-mcp --skill using-robot-mdgit clone --depth 1 https://github.com/RobotRegistryFoundation/robot-md-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/robotregistryfoundation/robot-md-mcp/using-robot-md)<a href="https://agentmods.dev/skills/robotregistryfoundation/robot-md-mcp/using-robot-md"><img src="https://agentmods.dev/badge/skills/robotregistryfoundation/robot-md-mcp/using-robot-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/robotregistryfoundation/robot-md-mcp/using-robot-md"><img src="https://agentmods.dev/badge/skills/robotregistryfoundation/robot-md-mcp/using-robot-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00079 | $0.04575 |
| Opus 5 | $0.00039 | $0.02287 |
| Sonnet 5 | $0.00016 | $0.00915 |
| Haiku 4.5 | $0.00008 | $0.00458 |
Grade A, and why
using-robot-md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using robot-md
First-time setup recipe
If you're seeing this on first plugin load, the operator has just installed the plugin and wants to wire up their robot. Run these commands in a terminal:
# 1) Install robot-md from PyPI. On Pi OS Bookworm+ you need --break-system-packages.
python3 -m pip install --user --break-system-packages robot-md
# 2) Initialize a manifest. Replace <name> + email; the preset is so-arm101 by default.
robot-md init <name> --preset so-arm101 --register --contact-email [email protected]
# 3) (Optional, but required for actual motion) Install the enforcement gateway.
robot-md install-gateway
# 4) Health check.
robot-md doctor
Each step should take ~30 s. Total cold-install time on a fresh Pi: under 2 minutes.
When something errors
Paste the error message back and we'll find the workaround. Common ones today:
- PEP 668
externally-managed-environment→pip installneeds--break-system-packageson Pi OS. The robot-md CLI handles this automatically insideinit, but the firstpip installstep is operator-driven. claude mcp listshows "Failed to connect" → either you haven'tcd'd into a directory with aROBOT.md, orROBOT_MD_PATHisn't set. Tryexport ROBOT_MD_PATH=$HOME/<name>/ROBOT.md./dev/ttyACM0permission denied → the gateway claims the device by design. Talk to the gateway at127.0.0.1:8080, not the device directly.
After install
Once robot-md doctor returns 0 fails, you're ready for the first prompt: try "what's the state of the robot?" — the MCP should answer from frontmatter resources without any motion. The remainder of this skill covers ongoing operation of the manifest.
Overview
This project has a ROBOT.md at its root — a single-file declaration of what the robot IS and what it CAN DO. robot-md is the CLI that reads, validates, renders, diagnoses, calibrates, and registers that file. It also ships an MCP server (registered as robot-md) that exposes the file to this agent session as resources.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 304 lines · 79 tokens per session scan A 719ab0cfbf18
using-robot-md is a skill published in the GitHub repository RobotRegistryFoundation/robot-md-mcp (1 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 79 tokens to every session and 4,575 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
gke-compute-classes
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.